Adaptive segmentation based on multi-classification model for dermoscopy images

Abstract

Segmentation accuracy of dermoscopy images is important in the computer-aided diagnosis of skin cancer and a wide variety of segmentation methods for dermoscopy images have been developed. Considering that each method has its strengths and weaknesses, a novel adaptive segmentation framework based on multi-classification model is proposed for dermoscopy images. Firstly, five patterns of images are summarized according to the factors influencing segmentation. Then the matching relation is established between each image pattern and its optimal segmentationmethod. Next, the given image is classified into one of the five patterns by the multi-classification model based on BP neural network. Finally, the optimal segmentation method for this image is selected according to the matching relation, and then the image is effectively segmented. Experiments show that the proposed method delivers better accuracy and more robust segmentation results compared with the other seven state-of-the-art methods.

Keywords

adaptive segmentation / feature extraction / pattern classification / dermoscopy image

References

[1] Siegel R, Ma J, Zou Z, Jemal A. Cancer statistics, 2014. CA: a Cancer Journal for Clinicians, 2014, 64(1): 9―29

[2] Di Leo G, Liguori C, Paolillo A, Sommella P. An improved procedure for the automatic detection of dermoscopy structures in digital ELMimages of skin lesions. In: Proceedings of the IEEE International Conference on Virtual Environment, Human-Computer Interfaces, and Measurement Systems. 2008, 190―194

[3] Soyer H P, Smolle J, Kerl H, Stettnre H. Early diagnosis of malignant melanoma by surface microscopy. The Lancet, 1987, 330(8562): 803

[4] Korotkov K, Garcia R. Computerized analysis of pigmented skin lesions: a review. Artificial Intelligence in Medicine, 2012, 56(2): 69―90

[5] Celebi M E, Iyatomi H, Schaefer G, Stoecker W V. Lesion border detection in dermoscopy images. Computerized Medical Imaging and Graphics, 2009, 33(2): 148―153

[6] Grana C, Pellacani G, Cucchiara R, Seidenari S. A new algorithm for border description of polarized light surface microscopic images of pigmented skin lesions. IEEE Transactions on Medical Imaging, 2003, 22(8): 959―964

[7] Silveira M, Nascimento J C, Marques J S, Marcal A R S, Mendonca T, Yarauchi S, Maeda J, Rozeira J. Comparison of segmentation methods for melanoma diagnosis in dermoscopy images. IEEE Journal of Selected Topics in Signal Processing, 2009, 3(1): 35―45

[8] Xu C, Prince J. Snakes, shapes, and gradient vector flow. IEEE Transactions on Image Process, 1998, 7(3): 359―369

[9] Nascimento J, Marques J S. Adaptive snakes using the EM algorithm. IEEE Transactions on Image Process, 2005, 14: 1678―1686

[10] Chan T, Sandberg B, Vese L. Active contours without edges for vectorvalued images. Journal of Visual Communication and Image Representation, 2000, 11(2): 130―141

[11] McLachlan G, Krishnan T. The EM Algorithm and Extensions. New York: John Wiley and Sons, 2007

[12] Maeda J, Kawano A, Saga S, Suzuki Y. Number-driven perceptual segmentation of natural color images for easy decision of optimal result. In: Proceedings of the IEEE international Conference on Image Processing. 2007, 2: 265―268

[13] Celebi M E, Aslandogan Y A, Stoecker W V, Iyatomi H, Dka H, Chen X H. Unsupervised border detection in dermoscopy images. Skin Research and Technology, 2007, 13(4): 454―462

[14] Celebi ME, Kingravi H A, Iyatomi H, Aslandogan Y A, Stoecker WV, Moss R H, Matters JM, Grichnik JM, Marghoob A A, Rabinovitz H S, Menzies S W. Border detection in dermoscopy images using statistical region merging. Skin Research and Technology, 2008, 14(3): 347―353

[15] Melli R, Grana C, Cucchiara R. Comparison of color clustering algorithms for segmentation of dermatological images. Medical Imaging. International Society for Optics and Photonics, 2006, 9: 61443S

[16] He Y, Xie F. Automatic skin lesion segmentation based on texture analysis and supervised learning. Lecture Notes in Computer Science, 2013, 7725: 330―341

[17] Wu Y, Xie F, Jiang Z, Meng R. Automatic skin lesion segmentation based on supervised learning. In: Proceedings of the 7th International Conference on Image and Graphics. 2013, 164―169

[18] Fukunaga K, Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transactions on Information Theory, 1975, 21(1): 32―40

[19] Xie F, Bovik A C. Automatic segmentation of dermoscopy images using self-generating neural networks seeded by genetic algorithm. Pattern Recognition, 2013, 46(3): 1012―1019

[20] Motoyarna H, Tanaka T, Tanka M, Oka H. Feature of malignant melanoma based on color information. In: Proceedings of SICE Annual Conference. 2004, 1: 230―233

[21] Alman D H, Berns R S, Snyder G D, Larsen W A. Performance testing of color-difference metrics using a color tolerance dataset. Color Research and Application, 1989, 14(3): 139―151

[22] Moroney N, Fairchild M, Hunt R, Li C, Luo M R, Newman T. The CIECAM02 color appearance model. Society for Imaging Science and Technology, 2002

[23] Freeman W T, Adelsonk E H. The design and use of steerable filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(9): 891―906

[24] Simoncelli E P, Freeman W T, Adeslon E H, Heeger D J. Shiftable multi-scale transforms. IEEE Transactions on Information Theory, 1992, 38(2): 587―607

[25] Abbas Q, Celebi M E, Serrano C, García I F, Ma G. Pattern classification of dermoscopy images: a perceptually uniform model. Pattern Recognition, 2013, 46(1): 86―97

[26] Xie F, Qin S, Jiang Z, Meng R. PDE-based unsupervised repair of hairoccluded information in dermoscopy images of melanoma. Computerized Medical Imaging and Graphics, 2009, 33(4): 275―282

[27] Stehman S V. Selecting and interpreting measures of thematic classification accuracy. Remote Sensing of Environment, 1997, 62(1): 77―89

[28] Mitchell T. Machine Learning. The MIT Press, 1997

[29] Suykens J A K, Vandewalle J. Least squares support vector machine classifiers. Neural Processing Letters, 1999, 9(3): 293―300

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg